Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Window
    -0.07
    leen
    -0.07
     refresh
    -0.07
    IFY
    -0.07
    prising
    -0.06
     establishes
    -0.06
    .refresh
    -0.06
     Workplace
    -0.06
    .simple
    -0.06
    swith
    -0.06
    POSITIVE LOGITS
     chiếm
    0.07
    �
    0.06
    rowth
    0.06
    daş
    0.06
     enamel
    0.06
     Trong
    0.06
    /disable
    0.06
    _ord
    0.06
     inmate
    0.06
     Rosenstein
    0.06
    Act Density 0.005%

    No Known Activations